24/7 Unmanned Operations as a Service

Feats of engineering enable autonomous production, space factories, and Machinery-as-a-Service business models. New data is required for the foundation of industrial AI algorithms.

Oct 20, 2024

Shop Talk

Capturing this week's zeitgeist

Feats of engineering come at all ages as these college students found in a surprising victory at a defense technology competition. You can get started building a pick-and-place system and maybe catch a rocket in the future:

Kaizen Blitz

📊 Survey Says
- SOTI’s 2024 Transportation & Logistics survey of 1,700 global professionals reveals that many fundamental issues still need to be addressed.
- Overcome common software implementation challenges with this Automated Warehouse Report.
- The Accel 2024 Euroscape report to read more on this year’s key cloud and AI trends and see the full list of the 100 companies to watch.
🗣️ Town Hall
- Lume Robotics CEO, Ranik Guidolini, discusses bringing customizable autonomy to Brazilian mining.
- Dean Kamen says inventing is easy, but innovating is hard.
- BeDimensional CEO, Vittorio Pellegrini, comments on his €20M raise for Few-Layer Graphene (FLG) and Few-Layer Hexagonal Boron Nitride (FLhBN or FLB) production.

Assembly Line

This week's most influential Industry 4.0 media.

Inside the world's first humanoid factory, where robots could eventually build themselves

🏢 Organizations: Agility Robotics

Vibration in Rotating Machinery: Analysis & Solutions

✍️ Author: Samir Jaber
🔖 Topics: Vibration Analysis, Predictive Maintenance
🏢 Organizations: SimScale, Hazleton Pumps

Unmanaged vibration introduces risks like mechanical wear, increased maintenance costs, and safety hazards for operators. Over time, this can result in machine downtime, loss of productivity, and higher operational costs. Addressing vibration early in the design phase or through continuous monitoring and vibration simulation helps maintain the reliability and performance of rotating machinery.

Hazleton Pumps, a manufacturer of heavy-duty pumps and pump systems, faced vibrational problems with one of their large, installed pumps weighing approximately 9 tons and operating at 800 RPM. Despite attempts to manually stabilize the pump with clamps, the vibration persisted, prompting the company to hire independent engineers. The engineers recommended significant modifications, including adding 500 kg of steel reinforcements, adjusting the subframe, and redesigning the bearing-to-shaft assembly, with an estimated cost of $40,000 per pump.

Instead, Hazleton turned to SimScale’s structural analysis tools to conduct a detailed multi-body modal analysis on the entire pump assembly. The simulation revealed that the eigenfrequency of the structure was around 780 RPM, meaning the pump was operating dangerously close to this resonance frequency. Equipped with this insight, Hazleton modified their operational procedures to avoid running the pump below 950 RPM, thus avoiding resonance-induced vibrations. They also implemented more cost-effective solutions, such as adding square tubing to the subframe, dramatically reducing costs compared to the original recommendations.

Progressing Space Systems Additive Manufacturing at Northrop Grumman with Steven Floyd

🏢 Organizations: Northrop Grumman, nTopology

Using AI to Detect Faulty Crimps

✍️ Author: Jinwoo Song
🔖 Topics: Quality Assurance, Multilayer Perceptron
🏢 Organizations: Dongguk University

Crimp force monitoring (CFM) has long been the standard for fault detection in wire assemblies. The technique can reliably detect many defects, including wrong strip length, missing strands, wrong wire cross section, wrong terminal, inconsistent terminal material, insulation in the crimp, wrong insertion depth, and wrong crimp height.

We propose a fault detection system that employs AI with regional selective data scaling (RSDS). RSDS generates synthetic abnormal data from reference data by performing upscaling or downscaling on specific regions of the data. This allows the fault detection system to efficiently train an AI model with a dataset comprised exclusively of normal operational data and still achieve high accuracy in detecting faults.

In this study, a multilayer perceptron (MLP) classification model was trained exclusively on normal data and was able to effectively distinguish between normal and abnormal conditions. To validate the system, 15 unique raw datasets from a real-world wire harness manufacturing facility were collected and tested with four anomaly detection algorithms: Isolation Forest, one-class autoencoders, k-means, and Histogram-Based Outlier Score (HBOS).

Revolutionizing Electronics Manufacturing: AI-Drive Digital Transformation

🏢 Organizations: Cognizant

Data Fuels Robotics Research

✍️ Author: Julia Hider
🏢 Organizations: Carnegie Mellon University

At Mill 19, the site of the Advanced Robotics for Manufacturing Institute and Carnegie Mellon University’s Manufacturing Futures Institute, robotics data provides the foundation for AI and digital twins.

The AI Data Foundry was started in March 2024 and is intended to be “a national center that collects and aggregates data for robots working in manufacturing settings in order to accelerate and develop AI and machine- learning algorithms that are relevant to various manufacturing tasks,” Fedder explains. This data will come from robots at ARM’s facility, as well as ARM’s members, performing all sorts of tasks: machine tending, welding, grinding, polishing, painting and more.

This data will provide the foundation for algorithms that will enable robots to work with challenging workpieces (such as flexible parts) or complete complex tasks (plugging cables into sockets or screwing nuts and bolts together). These tasks are more challenging to automate because they aren’t perfectly repetitive and therefore require so much data to program that gathering enough real-world data could be prohibitive. According to Fedder, synthetic, or computer-generated data could bridge this gap. Researchers can use synthetic data for tests and validate the results with real-world data.

Dock Automation Simplified: How Valeo Achieved 6X Speed

🏢 Organizations: Soft Robotics

New Product Introduction

Highlighting new and innovative facilities, processes, products, and services

Euro Manganese Announces Successful Completion of Demonstration Plant Continuous Operation Program

🔖 Topics: Autonomous Production
🏢 Organizations: Euro Manganese

Euro Manganese Inc. is pleased to announce the on-site Demonstration Plant successfully completed a 5-day continuous operation program for the production of high-purity electrolytic manganese metal at the Company’s Chvaletice Manganese Project in the Czech Republic. The Demonstration Plant achieved key technical targets which form part of the necessary conditions for accessing the next draw-down from the Orion financing package announced on November 28, 2023.

From October 7 to October 12, 2024, the qualified solution preparation and electrowinning module undertook a 24-hour-a-day, 5-day continuous operation program, with a target of producing a minimum of 132 kg HPEMM, with no more than 8 hours stoppage time. The purification step was run on batch basis to provide sufficient feedstock.

The Demonstration Plant operated as-designed and without interruption, achieving 100% reliability over the 5-day program (i.e. no stoppage time). Overall, 172 kg of HPEMM was produced, exceeding target production by over 30%.

Lyten Announces Plans to Build the World’s First Lithium-Sulfur Battery Gigafactory in Nevada

🏢 Organizations: Lyten

Lyten, the supermaterial applications company and global leader in Lithium-Sulfur batteries, announced plans to invest more than $1 billion to build the world’s first Lithium-Sulfur battery gigafactory. The facility will be located near Reno, Nevada, and will have the capability to produce up to 10 GWh of batteries annually at full scale. Phase 1 of the facility is scheduled to come online in 2027. Lyten’s factory will manufacture cathode active materials (CAM) and lithium metal anodes and complete assembly of lithium-sulfur battery cells in both cylindrical and pouch formats. Lyten has been manufacturing CAM and lithium metal anodes and assembling batteries at its semi-automated pilot facility in San Jose, Calif., since May 2023.

DENSO to Build a New Plant at the Zenmyo Plant

🏢 Organizations: DENSO

DENSO CORPORATION announced that it will build a new plant by expanding the site of the Zenmyo Plant in Nishio City, Aichi Prefecture. Construction will start in the first half of FY2025 and will be completed in January 2027, with production slated to start in the first half of FY2028. The total investment will be about 69 billion yen.

The new plant will be the first to incorporate DENSO’s next-generation plant concept from the planning phase. The plant will realize a creative workstyle based on digital infrastructure and automation technology, which will be deployed across the plant. It will also be capable of 24-hour unmanned operation, significantly improving production efficiency. Further, the aim is to build an environmentally friendly carbon-neutral plant by utilizing private power generation, which will use solar panels and hydrogen.

Business Transactions

This week's top funding events, acquisitions, and partnerships across industrial value chains.

Path Robotics Secures $100M of Venture Capital Funding

🔖 Topics: Funding Event
🏢 Organizations: Path Robotics, Matter Venture Partners, Drive Capital

Path Robotics continues to blaze the trail for tech and manufacturing in the US. Over the last 12 months, the artificial intelligence robotics startup has closed $100M in new investments led by Matter Venture Partners and Drive Capital, with participation from Yamaha Ventures, Taiwania Capital, MediaTek, Catapult Ventures, Gaingels, Addition, Tiger Global and Basis Set. Path Robotics has previously received venture backing from other prominent investors such as Drive Capital, Addition, Tiger Global, Basis Set, Lemnos, and SVB totalling $170M.

Path currently has two robotic welding products in the market. The AW-3 Robotic Welding Cell can handle large parts, as big as 70 feet long. The AF-1 Robotic Welding Cell can pick, fit, and weld parts without human intervention. Both robotic welding cells leverage vision systems, artificial intelligence, and machine learning to autonomously weld steel parts and are deployed in fabrication shops across the US and in Canada. Path Robotics also continues to double down on RaaS.

Agtonomy Closes $32.8M Series A to Accelerate AI-Driven Automation in Agriculture and Expand into Autonomous Industrial Equipment

🏢 Organizations: Agtonomy, Autotech Ventures

Agtonomy, the pioneer in AI-enabled automation software for agriculture and land maintenance, has raised an additional $10M to close its Series A round, bringing total funding to $32.8M. This significant investment, combined with Agtonomy’s commercial offerings and scalable business model, positions the company for accelerated growth and market expansion over the next few years. Autotech Ventures, the leading mobility venture fund, led the round. New investors include Rethink Food, Allison Transmission, and Black Forest Ventures. Existing backers Toyota Ventures, Flybridge, and Cavallo Partners continued their support.

Agtonomy’s immediate growth plans include scaling its West Coast technical team into new markets, expanding its 2025 paid pilot program for permanent crops by 500 percent, and developing technology solutions for other industrial markets that seek world-class automation to improve margins.

DeNexus Secures $17.5 Million in Series A Funding to Revolutionize Cyber Risk Management for Industrial Environments

🏢 Organizations: DeNexus, Punja Global Ventures

DeNexus, a leader in end-to-end cyber risk management for operational technology (OT), announced it has raised $17.5 million in a Series A funding round, positioning DeNexus to accelerate its growth and expand its innovative product offerings and markets.

The funding round was led by Punja Global Ventures, with investment also from AXA XL, Prosegur/SegTech and HCS Capital. As part of this investment, Rimmo Jolly, co-founder at Punja Global Ventures, will join DeNexus’ Board of Directors, while Libby Benet, Global Chief Underwriter Officer at AXA XL, will join as a Board Observer. With this new funding, DeNexus is well-positioned to address the growing need for comprehensive cyber risk management in industrial environments, helping organizations navigate the complex landscape of cybersecurity threats and regulations.

EnviCore Successfully Closes Seed Round to Scale Low-Carbon Cementitious Technology

🏢 Organizations: EnviCore, Companhia Siderúrgica Nacional

EnviCore, a Calgary-based leader in sustainable materials technology, announced the successful closing of its seed funding round, raising C$4.2 million. The round was led by prominent industry investors, including CSN Inova Ventures (the corporate venture capital arm of Companhia Siderúrgica Nacional, Brazil’s largest fully integrated steel producer), Heidelberg Materials, Techstars, Hillside Ventures, and Angel Investor Mark and Faye McGregor.

The funding will accelerate EnviCore’s mission to transform the cement industry by scaling the production of low-carbon supplementary cementitious materials (SCMs). EnviCore’s innovative technology reduces the carbon footprint of cement production by up to 30%, using recycled mineral feedstock. These SCMs can replace up to 35% of Portland cement in concrete, contributing to global sustainability and decarbonization efforts.

Kinaxis Announces Deal with ExxonMobil to Transform Energy Sector Supply Chains

🔖 Topics: Partnership
🏢 Organizations: Kinaxis, ExxonMobil

Kinaxis® (TSX:KXS), a global leader in end-to-end supply chain orchestration, announced a co-development deal with ExxonMobil, one of the largest integrated fuels, lubricants and chemical companies in the world, to create supply chain technology solutions designed specifically for the energy sector.

Kinaxis and ExxonMobil will focus on a supply and demand planning solution for the complicated fuel commodities market which has no industry-wide standard and which relies heavily on spreadsheets and other manual methods. The solution will enable integrated refinery-to-customer planning with timely data for the most accurate supply/demand planning, balancing and signaling.

Exponential Industry

Discussion about this post